Performance monitoring method and device of energy storage system and energy storage system

Abstract

The invention discloses a performance monitoring method and device of an energy storage system and the energy storage system.The performance monitoring method of the energy storage system comprises the steps that in response to receiving of battery cell working data of all battery cells in the energy storage system, a time sequence battery cell data set is obtained based on the incidence relation of the received battery cell working data in the time dimension; and predicting the performance of the energy storage system according to the time sequence cell data group to obtain a system performance index of the energy storage system. By adopting the performance monitoring method of the energy storage system provided by the embodiment of the invention, the accuracy of monitoring the performance of the energy storage system can be improved.

Description

Technical Field

[0001] The present application belongs to the field of energy storage technology, and in particular, relates to a performance monitoring method and device for an energy storage system, and an energy storage system. Background Art

[0002] Energy storage systems can be applied to various scenarios such as power systems, transportation, and industrial manufacturing. The requirements and monitoring methods for energy storage system performance are different in different scenarios. After a long period of operation, the performance of energy storage systems will degrade. Currently, the methods for monitoring energy storage systems mostly rely on monitoring single-dimensional data such as the voltage and current of the battery cells in the energy storage system. Large energy storage systems are usually equipped with thousands of battery cells, and long-term data monitoring of these battery cells is required to analyze the performance of the energy storage system. However, this method still has the disadvantage of being difficult to accurately evaluate the performance of the energy storage system. Summary of the invention

[0003] The embodiments of the present application provide a performance monitoring method, device and energy storage system for an energy storage system. The performance monitoring method for an energy storage system according to the embodiments of the present application can improve the accuracy of performance monitoring of the energy storage system.

[0004] In a first aspect, an embodiment of the present application provides a performance monitoring method for an energy storage system, the method comprising:

[0005] In response to receiving the cell working data of each cell in the energy storage system, based on the association relationship of the received cell working data of each cell in the time dimension, a time-series cell data group is obtained;

[0006] The performance of the energy storage system is predicted based on the time-series battery cell data group to obtain the system performance indicators of the energy storage system.

[0007] Optionally, the time dimension includes a horizontal time dimension and a vertical time dimension, and the battery cell working data includes battery cell operation data and battery cell environment data; in response to receiving the battery cell working data of each battery cell in the energy storage system, based on the association relationship between the received battery cell working data of each battery cell in the time dimension, a time series battery cell data group is obtained, including:

[0008] In response to receiving the cell working data of each cell in the energy storage system, based on the collection time of each cell working data received, preprocessing the cell working data at the same collection time as data of the same type to obtain preprocessed cell data, wherein the preprocessing includes at least one of data cleaning, data denoising and normalization processing;

[0009] Determine the pre-processed cell data of each cell at the same collection time as a time series cell data group under the horizontal time dimension;

[0010] The pre-processed cell data of the same cell at different collection times are determined as a time series cell data group in the longitudinal time dimension.

[0011] Optionally, the battery cell operation data includes at least one of the number of charge and discharge cycles, battery cell current, battery cell voltage and battery cell capacity; the battery cell environment data includes the battery cell operating temperature; the system performance index includes at least one of the system health index, the system capacity attenuation rate index and the charge and discharge efficiency index; the performance of the energy storage system is predicted according to the time series battery cell data group to obtain the system performance index of the energy storage system, including:

[0012] Extracting cell operation indicators from the time-series cell data group in the horizontal time dimension;

[0013] According to the battery cell operation indicators, the performance of the energy storage system is predicted through a pre-trained system performance monitoring model to obtain the system performance indicators of the energy storage system.

[0014] Optionally, after predicting the performance of the energy storage system based on the cell operation index and obtaining the system performance index of the energy storage system through a pre-trained system performance monitoring model, the method further includes:

[0015] According to the time-series battery cell data group under the horizontal time dimension and the time-series battery cell data group under the vertical time dimension, the system performance monitoring model is self-supervised learned, and the model parameters of the system performance monitoring model are updated;

[0016] The system performance monitoring model with updated model parameters is used to predict new system performance indicators of the energy storage system based on the time-series battery cell data group under the new horizontal time dimension.

[0017] Optionally, the cell operation index includes a voltage limit and a temperature limit; after extracting the cell operation index from the time series cell data group under the horizontal time dimension, the method further includes:

[0018] If the voltage limit exceeds the preset voltage range, or the temperature limit exceeds the preset temperature range, a fault alarm is sent to the user terminal.

[0019] Optionally, after predicting the performance of the energy storage system according to the time-series battery cell data group and obtaining the system performance index of the energy storage system, the method further includes:

[0020] According to the time series battery cell data group in the longitudinal time dimension, the fault monitoring of each battery cell in the energy storage system is performed through the pre-trained system performance monitoring model to obtain the fault monitoring result of each battery cell.

[0021] Optionally, the battery cell operation data includes at least one of the battery cell voltage and the battery cell internal resistance, and the battery cell environment data includes the battery cell operating temperature; according to the time series battery cell data group under the longitudinal time dimension, each battery cell in the energy storage system is monitored for faults by using a pre-trained system performance monitoring model to obtain a fault monitoring result of each battery cell, including:

[0022] By using the system performance monitoring model, a target sequential cell data group that meets the preset data failure trend is determined from the sequential cell data group under the longitudinal time dimension, and the cell corresponding to the target sequential cell data group is determined as the failed cell; or,

[0023] According to the time series cell data group of each cell in the longitudinal time dimension, the cell performance index of each cell is predicted through the system performance monitoring model.

[0024] Optionally, the cell performance index includes a cell failure time; after predicting the cell performance index of each cell through a system performance monitoring model according to the time series cell data group of each cell in the longitudinal time dimension, the method further includes:

[0025] Configure the trigger response to each battery cell failure time to send a fault alarm to the user terminal before the failure time of each battery cell is reached.

[0026] In a second aspect, an embodiment of the present application provides a performance monitoring device for an energy storage system, comprising:

[0027] A data receiving module, configured to, in response to receiving the cell working data of each cell in the energy storage system, obtain a time-series cell data group based on the association relationship of the received cell working data of each cell in the time dimension;

[0028] The performance monitoring module is used to predict the performance of the energy storage system based on the time-series battery cell data group to obtain the system performance indicators of the energy storage system.

[0029] In a third aspect, an embodiment of the present application provides an energy storage system, which includes a central data processing device and multiple battery cells in communication connection, wherein a data transmission device is provided in the battery cells, and the data transmission device is used to send the battery cell working data of the battery cell to the central data processing device, and the central data processing device is used to execute any of the above-mentioned performance monitoring methods of the energy storage system.

[0030] The embodiment of the present application takes into account the situation that there is a large amount of data monitoring in the long-term real-time monitoring of the battery cell working data of each battery cell in the energy storage system. Each battery cell in the energy storage system transmits its own battery cell working data, so that when responding to the reception of each battery cell working data, a time-series battery cell data group is obtained based on the correlation relationship of each battery cell working data received in the time dimension. In this way, it is convenient to monitor the battery cell working data of multiple dimensions of each battery cell, and the cost required for real-time monitoring of each battery cell working data can be reduced. In addition, the time-series battery cell data group is used to predict the performance of the energy storage system, which can obtain more accurate system performance indicators of the energy storage system, and facilitate the management of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The technical solution and beneficial effects of the present application will be made apparent by describing in detail the specific implementation methods of the present application in conjunction with the accompanying drawings.

[0032] Figure 1 is a schematic diagram of the structure of the energy storage system provided in the embodiment of the present application;

[0033] Figure 2 It is a flow chart of a performance monitoring method of an energy storage system provided in an embodiment of the present application;

[0034] Figure 3 It is a schematic diagram of performing a fault alarm according to a voltage limit or a temperature limit in the method provided in an embodiment of the present application;

[0035] Figure 4 is another flow chart of the performance monitoring method of the energy storage system provided in the embodiment of the present application;

[0036] Figure 5 is a schematic diagram of the structure of a performance monitoring device for an energy storage system provided in an embodiment of the present application;

[0037] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] Please refer to the drawings, where the same component symbols represent the same components. The principle of the present application is illustrated by implementing it in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application, which should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0039] See also Figure 1 , Figure 1It is a structural schematic diagram of an energy storage system provided in an embodiment of the present application, wherein the energy storage system comprises a central data processing device and a plurality of battery cells in communication connection, wherein a data transmission device is provided in the battery cell, and the data transmission device is used to send the battery cell working data of the battery cell to the central data processing device, and the central data processing device is used to respond to the reception of the battery cell working data of each battery cell in the energy storage system, and obtain a time series battery cell data group based on the correlation relationship of the received battery cell working data of each battery cell in the time dimension; and predict the performance of the energy storage system according to the time series battery cell data group to obtain the system performance index of the energy storage system.

[0040] In some embodiments, the battery cell is also communicatively connected to various sensors to collect relevant data of the battery cell. For example, the voltage sensor is used to collect the battery cell voltage of the battery cell, including the battery cell charging voltage and the battery cell discharging voltage. The current sensor is used to collect the battery cell current of the battery cell, including the battery cell charging current and the battery cell discharging current. The internal resistance sensor is used to collect the battery cell internal resistance of the battery cell. The temperature sensor is used to collect the battery cell operating temperature of the battery cell. The humidity sensor is used to collect the battery cell operating humidity of the battery cell. The state sensor is used to detect the discharge state and charging state of the battery cell. Here, only examples of sensor data collected by various sensors are given. The content covered by the battery cell working data can be determined based on the type of sensor connected to the battery cell in actual work.

[0041] Exemplarily, the battery cell further includes a clock module to obtain sensor data from various sensors according to a preset sampling frequency.

[0042] In addition, the battery cell is also used to process various sensor data received to convert various sensor data from analog data into digital signals. Here, the sensor data of the digital signal type is referred to as battery cell working data, which is convenient for subsequent transmission and processing of the battery cell working data.

[0043] In some embodiments, the battery cell further includes a storage module to cache the battery cell working data, and transmit the stored battery cell working data to the central data processing device at a preset transmission frequency. The storage module includes a high-speed cache to quickly and dynamically store the newly collected battery cell working data, thereby increasing the amount of battery cell working data stored in the high-speed cache, thereby assisting the central data processing device in improving data processing efficiency when performing subsequent processing on the battery cell working data.

[0044] Exemplarily, each battery cell can also be arranged to send its cached battery cell working data to the central data processing device after a preset period of time, thereby maintaining the consistency of the data received by the central data processing device, facilitating unified processing of the battery cell working data of each battery cell, balancing the data processing dimensions, and improving the accuracy of data processing.

[0045] In some embodiments, the time dimension includes a horizontal time dimension and a vertical time dimension, and the battery cell working data includes battery cell operation data and battery cell environment data; the central data processing device is also used to respond to the reception of the battery cell working data of each battery cell in the energy storage system, based on the collection time of the received battery cell working data of each battery cell, pre-process the battery cell working data at the same collection time as the same type of data to obtain pre-processed battery cell data, the pre-processing including at least one of data cleaning, data denoising and normalization processing; determine the pre-processed battery cell data of each battery cell at the same collection time as a time series battery cell data group under the horizontal time dimension; determine the pre-processed battery cell data of the same battery cell at different collection times as a time series battery cell data group under the vertical time dimension.

[0046] In some embodiments, the battery cell operation data includes at least one of the number of charge and discharge cycles, battery cell current, battery cell voltage and battery cell capacity, the battery cell environment data includes the battery cell operating temperature, and the system performance indicators include at least one of the system health indicators, the system capacity decay rate indicators and the charge and discharge efficiency indicators; the central data processing device is also used to extract the battery cell operation indicators from the time series battery cell data group under the horizontal time dimension; according to the battery cell operation indicators, the performance of the energy storage system is predicted by a pre-trained system performance monitoring model to obtain the system performance indicators of the energy storage system.

[0047] In some embodiments, the performance of the energy storage system is predicted based on the battery cell operation indicators through a pre-trained system performance monitoring model. After the system performance indicators of the energy storage system are obtained, the central data processing device is also used to perform self-supervised learning on the system performance monitoring model based on the time series battery cell data group under the horizontal time dimension and the time series battery cell data group under the vertical time dimension, and update the model parameters of the system performance monitoring model; the system performance monitoring model with updated model parameters is used to predict new system performance indicators of the energy storage system based on the time series battery cell data group under the new horizontal time dimension.

[0048] In some embodiments, the battery cell operation indicators include voltage limits and temperature limits; after extracting the battery cell operation indicators from the time-series battery cell data group under the horizontal time dimension, the central data processing device is also used to send a fault alarm to the user terminal if the voltage limit exceeds a preset voltage range, or the temperature limit exceeds a preset temperature range.

[0049] In some embodiments, after predicting the performance of the energy storage system based on the time-series battery cell data group and obtaining the system performance indicators of the energy storage system, the central data processing device is also used to perform fault monitoring on each battery cell in the energy storage system based on the time-series battery cell data group in the longitudinal time dimension through a pre-trained system performance monitoring model to obtain the fault monitoring results of each battery cell.

[0050] In some embodiments, the battery cell operation data includes at least one of the battery cell voltage and the battery cell internal resistance, and the battery cell environment data includes the battery cell operating temperature; the central data processing device is also used to determine, through a system performance monitoring model, a target sequential battery cell data group that meets a preset data failure trend from the sequential battery cell data group under the longitudinal time dimension, and determine the battery cell corresponding to the target sequential battery cell data group as a faulty battery cell; or, based on the sequential battery cell data group of each battery cell under the longitudinal time dimension, predict the battery cell performance index of each battery cell through a system performance monitoring model.

[0051] In some embodiments, the battery cell performance indicator includes a battery cell failure time; the central data processing device is further used to configure a trigger response to each battery cell failure time, so as to send a fault alarm to the user terminal before the failure time of each battery cell is reached.

[0052] The present application also provides a method for monitoring the performance of an energy storage system. Figure 2 , Figure 2 : is a flow chart of a performance monitoring method for an energy storage system provided in an embodiment of the present application. The performance monitoring method for an energy storage system can be applied to an energy storage system, a performance monitoring device for an energy storage system, and can also be applied to an electronic device, which can be integrated with a performance monitoring device for an energy storage system. The flow of the performance monitoring method for an energy storage system can include:

[0053] In 101 , in response to receiving the cell operation data of each cell in the energy storage system, a time-series cell data group is obtained based on the association relationship between the received cell operation data of each cell in the time dimension.

[0054] In 102, the performance of the energy storage system is predicted according to the time-series battery cell data group to obtain a system performance index of the energy storage system.

[0055] The energy storage system includes multiple communication-connected cells, and the cell working data of each cell received each time is used as new cell working data, and the remaining cell working data of each cell received in the previous period is used as historical cell working data. In this embodiment, the new cell working data and the historical cell working data are collectively referred to as the received cell working data.

[0056] Exemplarily, the cell working data includes cell operation data and cell environment data. The cell operation data includes, for example, cell voltage, cell current, cell internal resistance, cell capacity, number of charge and discharge cycles, cell charging efficiency, etc. The cell operating environment includes, for example, cell operating temperature, cell operating humidity, cell operating pressure, etc.

[0057] The following table shows the cell working data corresponding to each cell. The table takes 5 cells as examples, namely cell a, cell b, cell c, cell d and cell e. The cell voltage is represented by U, the cell current is represented by I, the cell internal resistance is represented by R, the cell capacity is represented by A, the number of charge and discharge cycles is represented by N, the cell charging efficiency is represented by η, the cell operating temperature is represented by K, the cell operating humidity is represented by H, and the cell operating pressure is represented by P.

[0058]

[0059] As mentioned above, each battery cell has corresponding battery cell working data at different collection times. In the longitudinal time dimension, each battery cell has corresponding battery cell working data at different collection times. For example, the battery cell working data of battery cell a at collection time T1 is represented by {Ua1, Ia1, Ra1, Aa1, Na1, ηa1, Ka1, Ha1, Pa1}. The battery cell working data of battery cell a at collection time T2 is represented by {Ua2, Ia2, Ra2, Aa2, Na2, ηa2, Ka2, Ha2, Pa2}. The battery cell working data of battery cell a at collection time T3 is represented by {Ua3, Ia3, Ra3, Aa3, Na3, ηa3, Ka3, Ha3, Pa3}. Battery a at collection time T n The battery cell working data represents {Ua n , Ia n , Ra n , Aa n , Na n , ηa n ,Ka n , Ha n ,Pa n}.

[0060] In the horizontal time dimension, each different battery cell has corresponding battery cell working data. For example, at the acquisition time T1, each of the five battery cells includes five battery cell working data. For example, the battery cell working data of battery cell a is represented by {Ua1, Ia1, Ra1, Aa1, Na1, ηa1, Ka1, Ha1, Pa1}, and the battery cell working data of battery cell b is represented by {Ub1, Ib1, Rb1, Ab1, Nb1, ηb1, Kb1, Hb1, Pb1}.}, the cell working data of battery cell c is represented by {Uc1, Ic1, Rc1, Ac1, Nc1, ηc1, Kc1, Hc1, Pc1}, the cell working data of battery cell d is represented by {Ud1, Id1, Rd1, Ad1, Nd1, ηd1, Kd1, Hd1, Pd1}, and the cell working data of battery cell e is represented by {Ue1, Ie1, Re1, Ae1, Ne1, ηe1, Ke1, He1, Pe1}.

[0061] As described above, the working data of each battery cell can be associated in the vertical time dimension, and the working data of each battery cell can also be associated in the horizontal time dimension to obtain a time-series battery cell data group. The embodiment of the present application can mine deeper battery cell working data characteristics by considering the vertical and horizontal associations of the working data of each battery cell in the time dimension, thereby predicting the performance of the energy storage system based on the time-series battery cell data group and obtaining more accurate system performance indicators of the energy storage system.

[0062] In some embodiments, 101 includes:

[0063] In response to receiving the cell working data of each cell in the energy storage system, based on the collection time of the received cell working data of each cell, preprocessing the cell working data at the same collection time as data of the same type to obtain preprocessed cell data, wherein the preprocessing includes at least one of data cleaning, data denoising and normalization processing;

[0064] Determine the pre-processed cell data of each cell at the same collection time as a time series cell data group under the horizontal time dimension;

[0065] The pre-processed cell data of the same cell at different collection times are determined as a time series cell data group in the longitudinal time dimension.

[0066] In this embodiment, the time dimension includes a horizontal time dimension and a vertical time dimension, and the battery cell working data includes battery cell operation data and battery cell environment data.

[0067] When preprocessing the cell working data of each cell, for each new cell working data received, the cell working data is first preprocessed as data of the same type from the horizontal time dimension. The same type of data here refers to data belonging to the same category in the cell working data, such as uniform preprocessing of the cell operation data of each cell at the same collection time, and uniform preprocessing of the cell environment data of each cell at the same collection time.

[0068] It can be seen that the battery cell operation data also includes the above-mentioned battery cell voltage, battery cell current, battery cell internal resistance, battery cell capacity, number of charge and discharge cycles, battery cell charging efficiency, etc. Under more detailed data types, for example, the battery cell voltage of each battery cell at the same collection time can be uniformly preprocessed, that is, the battery cell voltage {Ua1, Ub1, Uc1, Ud1, Ue1} of battery cell a, battery cell b, battery cell c, battery cell d and battery cell e at collection time T1 is uniformly preprocessed. For example, the battery cell current of each battery cell at the same collection time is uniformly preprocessed, that is, the battery cell current {Ia1, Ib1, Ic1, Id1, Ie1} of battery cell a, battery cell b, battery cell c, battery cell d and battery cell e at collection time T1 is uniformly preprocessed. It can be understood that the battery cell environment data can also be uniformly preprocessed through more detailed data types.

[0069] Exemplarily, the preprocessing method includes data cleaning, which includes processing missing values, removing duplicate values, removing outliers, etc. Among them, when processing missing values, it can be handled according to specific circumstances. For example, when there are fewer missing values, the missing values ​​can be directly deleted. When the missing values ​​are continuous, interpolation methods can be used to estimate the values ​​of unknown points through known data, such as linear interpolation, polynomial interpolation, or using statistical models such as regression analysis to predict missing values. In addition, the mean, median, mode, or common sense in a specific field can be used to fill in missing values ​​to maximize the retention of information in the original data.

[0070] The methods of removing outliers include directly deleting outliers. Or using alternative values ​​to replace outliers, commonly used alternative values ​​include median, mean, mode, etc. You can also use logarithmic transformation, square root transformation or other appropriate mathematical transformations to make it closer to the normal range. Statistical methods such as box plots, local outlier factor method (LOF method), clustering methods or methods based on robust Mahalanobis distance can be used to detect outliers.

[0071] The data cleaning preprocessing method can effectively identify outliers in the time series battery data set, thereby removing outliers to facilitate subsequent data analysis. It is also possible to avoid repeated calculations by removing duplicate values, thereby saving computing resources and improving the accuracy of calculation results. It is also possible to retain the original data of the time series battery data set to the maximum extent by removing missing values, thereby ensuring the data integrity of the time series battery data set.

[0072] In addition, in the process of transmitting sensor data by various sensors, data noise is easily generated due to factors such as electromagnetic interference and electronic device signal processing, resulting in offset and fluctuation of data such as battery cell voltage and battery cell temperature collected by the sensor, and data errors occur. Therefore, the preprocessing provided in the embodiment of the present application also includes denoising the time series battery cell data group. Among them, the denoising process can be denoising by a filtering method, that is, using a low-pass filter to remove high-frequency noise, and using a high-pass filter can retain the edge information of the data. Of course, the filtering method also includes filtering by using a mean filtering algorithm, a median filtering algorithm, a weighted sliding average, and the like.

[0073] Furthermore, in order to facilitate the unified analysis of the sequential battery cell data group, it is also normalized or standardized, which can improve the convergence speed and generalization performance of the algorithm and improve the robustness and accuracy of the model.

[0074] In this embodiment, after obtaining the pre-processed cell data, each pre-processed cell data is further divided based on the time dimension, wherein the pre-processed cell data of each cell at the same collection time is referred to as a time series cell data group under the horizontal time dimension. For example, the pre-processed cell data of multiple cells at the collection time T1 (such as the pre-processed cell voltage, cell current, cell capacity, number of charge and discharge cycles, cell operating temperature, etc.) is referred to as a time series cell data group of each cell under the horizontal time dimension. The pre-processed cell data of the same cell at different collection times is also referred to as a time series cell data group under the vertical time dimension, for example, the pre-processed cell data of cell a at collection times T1, T2, T3, T4, T5, T6, T7, T8, T9, T10, T11, T12, T13, T14, T15, T16, T17, T18, T19, T20, T21, T22, T30, T43, T54, T65, T76, T87, T9 n The preprocessed cell data (such as the preprocessed cell voltage, cell current, cell capacity, number of charge and discharge cycles, cell operating temperature, etc.) is called the time series cell data group of cell a in the longitudinal time dimension.

[0075] In the embodiment of the present application, by uniformly preprocessing the cell working data of each battery cell, it is possible to avoid the problem of repeated calculations, reduce the time consumption of calculations, and further reduce the waste of computing resources, and improve the utilization rate of computing resources. Furthermore, it is also possible to ensure the uniformity and accuracy of the processing of the cell working data of each battery cell. Compared with the prior art of collecting the cell working data of the battery cell in real time and preprocessing the real-time collected cell working data, the embodiment of the present application can also avoid the processing errors caused by processing the cell working data of each battery cell in batches, and by performing the same type of processing on the cell working data of different battery cells in the same time dimension, it is possible to improve the effectiveness of data processing, so that when it is applied to the subsequent performance prediction of the energy storage system, more accurate system performance indicators can be obtained.

[0076] In some embodiments, 102 includes:

[0077] 1021. Extracting a cell operation index from the time series cell data group in the horizontal time dimension;

[0078] 1022. According to the battery cell operation indicators, the performance of the energy storage system is predicted through a pre-trained system performance monitoring model to obtain the system performance indicators of the energy storage system.

[0079] In this embodiment, the battery cell operation data includes at least one of the number of charge and discharge cycles, battery cell current, battery cell voltage and battery cell capacity, the battery cell environmental data includes the battery cell operating temperature, and the system performance indicators include at least one of the system health indicators, the system capacity attenuation rate indicators and the charge and discharge efficiency indicators.

[0080] When extracting cell operation indicators from the sequential cell data group in the horizontal time dimension, cell operation indicators that characterize the balanced performance of the cell can be extracted. For example, the voltage average value, voltage fluctuation amplitude, etc. are extracted from the cell voltage of the sequential cell data group, where the voltage average value reflects the overall state of the cell, and the voltage fluctuation amplitude reflects the uneven electrodes or local short circuits inside the cell. For example, the maximum temperature, minimum temperature, and temperature distribution are extracted from the cell operating temperature of the sequential cell data group, where the maximum temperature refers to the thermal runaway of the battery, which is an important indicator of battery safety, the minimum temperature can reflect the degree of influence of the ambient temperature on the cell, and the temperature distribution can reflect the consistency of the temperature of each cell.

[0081] System health indicators include SOC (State of Charge) and SOH (State of Health). SOC indicates the state of charge of the entire battery cell in the energy storage system, that is, the percentage of the current remaining power of the battery cell to the fully charged state. SOH refers to the health status of the energy storage system, which reflects the degree of performance degradation of each battery cell in the energy storage system. As the energy storage system is used, its performance will gradually decline, including a decrease in energy density, power output, and cycle life. SOH evaluates the health of the energy storage system by comparing the current performance of the energy storage system with the performance in a brand new state. It is an important indicator for evaluating the aging degree of the energy storage system and can also reflect the working life of the overall battery cell in the energy storage system. When predicting the system health indicators of the energy storage system, predictions can be made based on the battery cell operation data and battery cell operating temperature in the time series battery cell data group.

[0082] The system capacity decay rate index refers to the rate at which the capacity or performance of an energy storage system decreases over time during its life cycle. When predicting the system capacity decay rate index of an energy storage system, the prediction can be made based on the cell capacity in the time series cell data group.

[0083] The charge and discharge efficiency index reflects the energy conversion efficiency of the energy storage system during the charge and discharge process. When predicting the charge and discharge efficiency index of the energy storage system, the charge and discharge efficiency of the energy storage system can be obtained by analyzing the energy loss of each battery cell during the charge and discharge process.

[0084] Exemplarily, the cell operation index can be extracted from the time series cell data set under the horizontal time dimension by including recurrent neural network (RNN), convolutional neural network (CNN), Transformer, long short-term memory network (LSTM), etc. In this way, the nonlinear relationship between each data in each time series cell data set can be processed more effectively, and deeper features and their correlation relationships can be extracted, so that when the cell operation index is used for model prediction, the performance, generalization ability and interpretability of the model can be improved.

[0085] It is also possible to pre-train a system performance monitoring model so that the trained system performance monitoring model can be used to predict the performance of the energy storage system. Specifically, the cell operation index can be used as the input of the system performance monitoring model, and the performance of the energy storage system can be predicted through the system performance monitoring model, and the system performance index of the energy storage system can be output.

[0086] When training a system performance monitoring model, for example, you can first select a suitable model, such as a linear regression model, support vector machine, decision tree model, etc. Then divide the sample data set into a training set, a validation set, and a test set. The training set is used to train the model, the validation set is used to adjust the model parameters and evaluate the model performance, and the test set is used to finally evaluate the generalization ability of the model. By using the training set to iterate the model multiple times, the weights and parameters of the model are continuously adjusted so that the model meets the preset iteration conditions, and the trained system performance monitoring model is obtained.

[0087] In some embodiments, after 1021, the method further includes:

[0088] If the voltage limit exceeds the preset voltage range, or the temperature limit exceeds the preset temperature range, a fault alarm is sent to the user terminal.

[0089] In this embodiment, the battery cell operation index includes a voltage limit and a temperature limit.

[0090] Among them, the voltage limit includes the maximum value of the battery cell voltage and the minimum value of the battery cell voltage. The temperature limit includes the maximum value of the battery cell operating temperature and the minimum value of the battery cell operating temperature. The preset voltage range can be a numerical interval from the lowest value of the battery cell voltage to the highest value of the battery cell voltage when the energy storage system is working normally, or a voltage numerical interval set when the energy storage system leaves the factory, or a voltage numerical interval set by the user. The preset temperature range can be set according to the temperature range of the location of the energy storage system, or it can be set according to the numerical interval from the lowest value of the operating temperature to the highest value of the operating temperature when the energy storage system is running, or it can be set by the user.

[0091] Specifically, see Figure 3 , Figure 3 This is a schematic diagram of a fault alarm according to a voltage limit or a temperature limit in a method provided in an embodiment of the present application. When the voltage limit exceeds a preset voltage range, a fault alarm can be sent to a user terminal. Or when the temperature limit exceeds a preset temperature range, a fault alarm can be sent to a user terminal.

[0092] Among them, the method of sending fault alarms includes but is not limited to telephone prompts, SMS prompts and information prompts. The method of information prompts is, for example, pushing fault information through application software, such as pop-up prompts, message prompts, etc.

[0093] By sending fault alarms, users can be notified not only of the existence of faults in the energy storage system, but also of the location of the specific faulty cells in the energy storage system and the cause of the fault, etc. This reminds users to respond to the faults in the energy storage system immediately and ensure the subsequent normal operation of the energy storage system.

[0094] In some embodiments, the countermeasures for energy storage system failures, after sending the failure alarm to the user terminal, further include:

[0095] The protection mechanism is activated, and control instructions are sent to the circuit breakers and protection devices of the energy storage system to instruct the energy storage system to power off, activate overvoltage prevention and control, and activate thermal failure prevention and control.

[0096] For example, a control command can be sent to the circuit breaker of the energy storage system to control the power outage of the energy storage system. By remotely controlling the circuit breaker, possible equipment damage, fire and other accidents can be avoided to ensure the safety of the operating environment and equipment of the energy storage system. For another example, a control command can be sent to the protection device of the energy storage system to control it to start overvoltage prevention and / or thermal failure prevention of the energy storage system to ensure the safety and stability of the operation of the energy storage system.

[0097] In some embodiments, after 102, the method further includes:

[0098] According to the time-series battery cell data group under the horizontal time dimension and the time-series battery cell data group under the vertical time dimension, the system performance monitoring model is self-supervised learned, and the model parameters of the system performance monitoring model are updated;

[0099] The system performance monitoring model with updated model parameters is used to predict new system performance indicators of the energy storage system based on the time-series battery cell data group under the new horizontal time dimension.

[0100] Among them, the vertical time dimension includes multiple collection times, each collection time corresponds to a time series battery cell data group, the time series battery cell data group under the horizontal time dimension is called the historical time series battery cell data group of the collection time, and different sampling times correspond to multiple historical time series battery cell data groups in time series.

[0101] In this embodiment, a self-supervised learning mechanism of the system performance monitoring model is constructed to allow the system performance monitoring model to predict and process new unlabeled time-series battery cell data groups by learning from historical time-series battery cell data groups, without the need to manually label the historical time-series battery cell data groups. Among them, the system performance monitoring model learns the relationship and transformation between the data in the historical time-series battery cell data groups to automatically generate labels, so as to continue to train the system performance monitoring model based on the labels. In the process of continuing to train the system performance monitoring model, part of the historical time-series battery cell data groups can also be used as a verification set to evaluate the performance of the system performance monitoring model, and then adjust the model parameters, thereby improving the performance and adaptability of the system performance monitoring model.

[0102] In summary, by predicting the system performance indicators of the energy storage system, the performance of the energy storage system can be predicted more accurately, and the failure of the energy storage system can be discovered in time, thereby reducing the risk of failure of the energy storage system. In addition, the system performance indicators of the energy storage system are further predicted by using the time-series battery cell data group and the system performance monitoring model. On the basis of improving the accuracy of the energy storage system performance prediction, it can also dynamically adapt to the changes in the battery cell working data of each battery cell in the energy storage system, enhance the monitoring of the energy storage system performance, reduce labor costs, and optimize the cost required for monitoring the performance of the energy storage system.

[0103] In addition, the performance monitoring method of the energy storage system provided in the embodiment of the present application is also used to perform fault monitoring on each battery cell of the energy storage system. Figure 4 , Figure 4 It is another flow chart of the performance monitoring method of the energy storage system provided in the embodiment of the present application.

[0104] In 201 , in response to receiving the cell operation data of each cell in the energy storage system, a time-series cell data group is obtained based on the association relationship between the received cell operation data of each cell in the time dimension.

[0105] In 202 , according to the time series battery cell data group in the longitudinal time dimension, each battery cell in the energy storage system is monitored for faults by using a pre-trained system performance monitoring model to obtain a fault monitoring result of each battery cell.

[0106] The method of determining the time-series battery cell data group and training the system performance monitoring model in this embodiment can refer to the contents mentioned in the above embodiment, which will not be repeated here. The battery cell operation data in this embodiment includes at least one of the battery cell voltage and the battery cell internal resistance, and the battery cell environment data includes the battery cell operating temperature.

[0107] It can be seen that the system performance monitoring model can not only predict the system performance indicators of the energy storage system, but also monitor the faults of each battery cell in the energy storage system, thereby obtaining the fault monitoring results of each battery cell.

[0108] In some embodiments, 202 includes:

[0109] Through the system performance monitoring model, a target sequential cell data group that meets the preset data failure trend is determined from the sequential cell data group under the longitudinal time dimension, and the cell corresponding to the target sequential cell data group is determined as the faulty cell.

[0110] Among them, each battery cell has a time-series battery cell data group arranged in chronological order, and the battery cell performance trend of the battery cell corresponding to each time-series battery cell data group can be predicted through the system performance monitoring model. For example, if the battery cell voltage, battery cell operating temperature, and battery cell internal resistance of a certain battery cell exceed the limit, the battery cell is determined to be a faulty battery cell. For example, the battery cell voltage fluctuates within the voltage range under normal circumstances. If the battery cell voltage of a certain battery cell shows a gradual downward or upward trend, it means that the change trend of the battery cell voltage does not match the normal voltage trend, but matches the preset voltage fault trend, so that the battery cell performance of the battery cell is determined to be declining, that is, the battery cell is a faulty battery cell.

[0111] After the faulty battery cell is identified, a fault alarm can also be sent to the user terminal to remind the user of the faulty battery cell and the cause of the fault of the faulty battery cell, so that the user can replace the faulty battery cell in time or repair the faulty battery cell, thereby ensuring the operating efficiency of the energy storage system.

[0112] In some embodiments, 202 includes:

[0113] According to the time series cell data group of each cell in the longitudinal time dimension, the cell performance index of each cell is predicted through the system performance monitoring model.

[0114] The system performance monitoring model can also be used to predict the performance indicators of each battery cell, including the cycle life of the battery cell, the calendar life of the battery cell, the time of future failure, etc.

[0115] By predicting the cell performance indicators of each battery cell, while taking into account the performance monitoring of the energy storage system, it is also possible to timely predict the cell performance indicators of each battery cell, thereby realizing all-round performance monitoring of the energy storage system, thereby facilitating the location of various problems that arise in the energy storage system, facilitating the maintenance and management of the energy storage system, thereby reducing the resource consumption of managing the energy storage system and improving the efficiency of managing the energy storage system.

[0116] In some embodiments, after 202, the method further includes:

[0117] Configure the trigger response to each battery cell failure time to send a fault alarm to the user terminal before the failure time of each battery cell is reached.

[0118] As mentioned above, the cell failure time of each cell can be predicted through the system performance monitoring model based on the sequential cell data group of each cell in the longitudinal time dimension. Therefore, a trigger response of the cell failure time is configured for the faulty cell whose cell failure time is less than the preset time threshold. The trigger response refers to sending a fault alarm to the user terminal in advance before the failure time of a certain cell arrives to remind the user that the cell is expected to fail at the failure time, thereby providing the user with sufficient preparation time to maintain the cell in time and avoid the use failure of the cell in the future, thereby ensuring that the energy storage system operates uninterruptedly with high performance.

[0119] It is understandable that the cell failure time can be determined according to the degree of cell performance degradation. When the cell degradation degree is high, the cell will fail as early as possible, that is, the cell failure time is small, or the cell failure time is close to the current time. Therefore, by comparing the cell failure time with the preset time threshold, the user can be reasonably informed of the expected cell failure time of the cell with a high probability of failure as soon as possible.

[0120] For example, the cell capacity decay rate can be determined through the cell capacity change in the time-series cell data group, so as to predict the cell life decay rate, and the cell failure time of the cell can be obtained based on the life decay rate and the limited use decay index.

[0121] In addition, the cell performance indicators of each battery cell are also related to the system performance indicators of the energy storage system. For example, if there are many failed battery cells in the energy storage system, or the frequency of battery cell failure is high, the system performance indicators of the energy storage system will decrease when the performance of the energy storage system is subsequently predicted.

[0122] In some embodiments, the cell working data, sequential cell data, system performance indicators, cell operation indicators, and cell performance indicators of each cell in the energy storage system can also be uploaded to a cloud server to store various types of data in the cloud, making it easier to access the cloud server to obtain the corresponding data later, and reducing the storage pressure of the energy storage system for long-term data storage, thereby improving the operating efficiency of the energy storage system.

[0123] In summary, the performance monitoring method and system of the energy storage system provided in the embodiment of the present application reduces the hardware cost by placing the collection of the cell working data of the cell at the cell end, and the central data processing device is only responsible for the unified reception and processing of the cell working data, thereby realizing the orderliness of the central data processing device processing the cell working data of each cell, ensuring the effectiveness of subsequent data processing, and by receiving multiple cell working data of each cell at one time, it is possible to avoid repeated processing of data, balance the data processing dimension, and improve the accuracy of data processing. In addition, by deploying a system performance monitoring model, the system performance indicators of the energy storage system and the cell performance indicators of each cell are predicted by self-supervised learning, so as to timely discover faults and give alarms, and there is no need to judge and analyze the fault time, thereby reducing the operation and maintenance cost, realizing intelligent early warning of the energy storage system, improving the effectiveness of management and monitoring of the energy storage system, and avoiding future failures of the energy storage system. Furthermore, the system performance monitoring model can also perform adaptive optimization and iteration of the model based on historical data to adapt to the dynamic data changes of the energy storage system, thereby improving the reliability and prediction efficiency of the model.

[0124] See also Figure 5 , Figure 5 300 is a schematic diagram of the structure of a performance monitoring device for an energy storage system provided in an embodiment of the present application. The performance monitoring device 300 for an energy storage system may include: a data receiving module 301 and a performance monitoring module 302 .

[0125] The data receiving module 301 is used to obtain a time-series cell data group in response to receiving the cell working data of each cell in the energy storage system based on the association relationship of the received cell working data of each cell in the time dimension;

[0126] The performance monitoring module 302 is used to predict the performance of the energy storage system according to the time-series battery cell data group to obtain the system performance index of the energy storage system.

[0127] In one embodiment, the time dimension includes a horizontal time dimension and a vertical time dimension, and the battery cell working data includes battery cell operation data and battery cell environment data; the data receiving module 301 can be used to: in response to receiving the battery cell working data of each battery cell in the energy storage system, based on the collection time of each received battery cell working data, preprocess the battery cell working data at the same collection time as the same type of data to obtain preprocessed battery cell data, the preprocessing including at least one of data cleaning, data denoising and normalization processing; determine the preprocessed battery cell data of each battery cell at the same collection time as a time series battery cell data group under the horizontal time dimension; determine the preprocessed battery cell data of the same battery cell at different collection times as a time series battery cell data group under the vertical time dimension.

[0128] In one embodiment, the battery cell operation data includes at least one of the number of charge and discharge cycles, battery cell current, battery cell voltage and battery cell capacity, the battery cell environment data includes the battery cell operating temperature, and the system performance indicators include at least one of the system health indicators, the system capacity decay rate indicators and the charge and discharge efficiency indicators; the performance monitoring module 302 can be used to: extract the battery cell operation indicators from the time series battery cell data group under the horizontal time dimension; according to the battery cell operation indicators, predict the performance of the energy storage system through a pre-trained system performance monitoring model to obtain the system performance indicators of the energy storage system.

[0129] In one embodiment, the performance of the energy storage system is predicted based on the battery cell operation indicators through a pre-trained system performance monitoring model. After the system performance indicators of the energy storage system are obtained, the performance monitoring module 302 can be used to: perform self-supervised learning on the system performance monitoring model based on the time series battery cell data group under the horizontal time dimension and the time series battery cell data group under the vertical time dimension, and update the model parameters of the system performance monitoring model; use the system performance monitoring model with updated model parameters to predict new system performance indicators of the energy storage system based on the time series battery cell data group under the new horizontal time dimension.

[0130] In one embodiment, the battery cell operation indicators include voltage limit and temperature limit; after extracting the battery cell operation indicators from the time-series battery cell data group under the horizontal time dimension, the performance monitoring module 302 can be used to: if the voltage limit exceeds the preset voltage range, or the temperature limit exceeds the preset temperature range, a fault alarm is sent to the user terminal.

[0131] In one implementation, the performance monitoring module 302 may be used to: perform fault monitoring on each battery cell in the energy storage system according to the time-series battery cell data group in the longitudinal time dimension through a pre-trained system performance monitoring model to obtain a fault monitoring result for each battery cell.

[0132] In one embodiment, the battery cell operation data includes at least one of the battery cell voltage and the battery cell internal resistance, and the battery cell environment data includes the battery cell operating temperature; the performance monitoring module 302 can be used to: determine the target sequential battery cell data group that meets the preset data failure trend from the sequential battery cell data group under the longitudinal time dimension through the system performance monitoring model, and determine the battery cell corresponding to the target sequential battery cell data group as the faulty battery cell; or, predict the battery cell performance index of each battery cell through the system performance monitoring model according to the sequential battery cell data group of each battery cell under the longitudinal time dimension.

[0133] In one embodiment, the battery cell performance indicators include battery cell failure time; after predicting the battery cell performance indicators of each battery cell through a system performance monitoring model based on the time-series battery cell data group of each battery cell in the longitudinal time dimension, the performance monitoring module 302 can be used to: configure a trigger response to the failure time of each battery cell, so as to send a fault alarm to the user terminal before the failure time of each battery cell is reached.

[0134] The performance monitoring device of the energy storage system provided in the embodiment of the present application and the performance monitoring method of the energy storage system in the above embodiment belong to the same concept. Any method provided in the embodiment of the performance monitoring method of the energy storage system can be run on the performance monitoring device of the energy storage system. The specific implementation process is detailed in the embodiment of the performance monitoring method of the energy storage system, which will not be repeated here.

[0135] It can be understood that the performance monitoring device of the energy storage system provided in the embodiment of the present application can be integrated into the energy storage system or integrated into a server, and the physical form of the performance monitoring device of the energy storage system can also be a chip.

[0136] See also Figure 6 , Figure 6 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers.

[0137] An embodiment of the present application further provides an electronic device, the electronic device 400 includes a memory 401 and a processor 402, the processor 402 is used to execute the process in the performance monitoring method of the energy storage system provided in this embodiment by calling the computer program stored in the memory 401.

[0138] Those skilled in the art will understand that Figure 6 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0139] The application programs stored in the memory 401 include computer programs. The processor 402 executes various functional applications and data processing by running the computer programs stored in the memory 401 .

[0140] The processor 402 is the control center of the electronic device. It uses various interfaces and lines to connect various parts of the entire electronic device. It executes various functions of the electronic device and processes data by running or executing computer programs stored in the memory 401 and calling data stored in the memory 401, thereby monitoring the electronic device as a whole.

[0141] In this embodiment, the processor 402 in the electronic device will load the executable code corresponding to the process of one or more application programs into the memory 401 according to the following instructions, and the processor 402 will run the application program stored in the memory 401 to execute:

[0142] In response to receiving the cell working data of each cell in the energy storage system, based on the association relationship of the received cell working data of each cell in the time dimension, a time-series cell data group is obtained;

[0143] The performance of the energy storage system is predicted based on the time-series battery cell data group to obtain the system performance indicators of the energy storage system.

[0144] In the above embodiments, the description of each embodiment has its own emphasis. For the part that is not described in detail in a certain embodiment, please refer to the detailed description of the performance monitoring method of the energy storage system above, which will not be repeated here.

[0145] It should be noted that, for the performance monitoring method of the energy storage system in the embodiment of the present application, a person of ordinary skill in the art can understand that all or part of the process of implementing the performance monitoring method of the energy storage system in the embodiment of the present application can be completed by controlling the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, such as a memory, and executed by at least one processor, and the execution process may include the process of the embodiment of the performance monitoring method of the energy storage system. Among them, the computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), etc.

[0146] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed on a computer, the computer executes the process in the performance monitoring method of the energy storage system provided in this embodiment.

[0147] For the performance monitoring device of the energy storage system of the embodiment of the present application, each functional module can be integrated into a processing chip, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium, such as a read-only memory, a disk or an optical disk.

[0148] The above is a detailed introduction to the performance monitoring method, device and energy storage system of the energy storage system provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A performance monitoring method for an energy storage system, characterized in that: The method comprises: In response to receiving the cell working data of each cell in the energy storage system, based on the association relationship of the received cell working data of each cell in the time dimension, a time-series cell data group is obtained; The performance of the energy storage system is predicted according to the time-series battery cell data group to obtain a system performance index of the energy storage system.

2. The method for monitoring the performance of an energy storage system according to claim 1, characterized in that: The time dimension includes a horizontal time dimension and a vertical time dimension, and the battery cell working data includes battery cell operation data and battery cell environment data; The obtaining of a time-series cell data group based on the association relationship of the received cell working data of each cell in the time dimension includes: Based on the collection time of each battery cell working data that has been received, preprocessing the battery cell working data at the same collection time as data of the same type to obtain preprocessed battery cell data, wherein the preprocessing includes at least one of data cleaning, data denoising and normalization processing; Determine the pre-processed cell data of each cell at the same collection time as a time series cell data group under the horizontal time dimension; The pre-processed cell data of the same cell at different collection times are determined as a time series cell data group in the longitudinal time dimension.

3. The method for monitoring the performance of an energy storage system according to claim 2, characterized in that: The battery cell operation data includes at least one of the number of charge and discharge cycles, battery cell current, battery cell voltage and battery cell capacity; the battery cell environment data includes the battery cell operating temperature; and the system performance index includes at least one of the system health index, the system capacity attenuation rate index and the charge and discharge efficiency index; The predicting the performance of the energy storage system according to the time-series battery cell data group to obtain the system performance index of the energy storage system includes: Extracting a cell operation index from the time-series cell data group under the horizontal time dimension; According to the battery cell operation index, the performance of the energy storage system is predicted by a pre-trained system performance monitoring model to obtain the system performance index of the energy storage system.

4. The method for monitoring the performance of an energy storage system according to claim 3, characterized in that: The method further comprises: According to the time-series battery cell data group under the horizontal time dimension and the time-series battery cell data group under the vertical time dimension, self-supervised learning is performed on the system performance monitoring model to update model parameters of the system performance monitoring model; The system performance monitoring model after updating the model parameters is used to predict new system performance indicators of the energy storage system according to the time-series battery cell data group under the new horizontal time dimension.

5. The method for monitoring the performance of an energy storage system according to claim 3, characterized in that: The battery cell operation indicators include voltage limit and temperature limit; The method further comprises: If the voltage limit exceeds a preset voltage range, or the temperature limit exceeds a preset temperature range, a fault alarm is sent to the user terminal.

6. The method for monitoring the performance of an energy storage system according to any one of claims 2 to 5, characterized in that: The method further comprises: According to the time-series battery cell data group under the longitudinal time dimension, fault monitoring is performed on each battery cell in the energy storage system through a pre-trained system performance monitoring model to obtain a fault monitoring result of each battery cell.

7. The method for monitoring the performance of an energy storage system according to claim 6, characterized in that: The battery cell operation data includes at least one of the battery cell voltage and the battery cell internal resistance, and the battery cell environment data includes the battery cell operating temperature; According to the time series battery cell data group under the longitudinal time dimension, the fault monitoring of each battery cell in the energy storage system is performed by using a pre-trained system performance monitoring model to obtain the fault monitoring result of each battery cell, including: By using the system performance monitoring model, a target sequential cell data group that meets the preset data failure trend is determined from the sequential cell data group under the longitudinal time dimension, and the cell corresponding to the target sequential cell data group is determined as a failed cell; or According to the time series battery cell data group of each battery cell in the longitudinal time dimension, the battery cell performance index of each battery cell is predicted by the system performance monitoring model.

8. The method for monitoring the performance of an energy storage system according to claim 7, characterized in that: The battery cell performance indicators include battery cell failure time; The method further comprises: A trigger response to each of the battery cell failure times is configured to send a failure alarm to a user terminal before each of the battery cell failure times is reached.

9. A performance monitoring device for an energy storage system, characterized in that: include: A data receiving module, configured to, in response to receiving the cell working data of each cell in the energy storage system, obtain a time-series cell data group based on the association relationship of the received cell working data of each cell in the time dimension; The performance monitoring module is used to predict the performance of the energy storage system according to the time-series battery cell data group to obtain the system performance index of the energy storage system.

10. An energy storage system, characterized in that: The energy storage system includes a central data processing device and a plurality of battery cells in communication connection. The battery cells are provided with data transmission devices for sending the battery cell working data of the battery cells to the central data processing device. The central data processing device is used to execute the performance monitoring method of the energy storage system as described in any one of claims 1 to 8.

Images